A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS:

CASE STUDY

Author(s): Joel Murataj a , Prof. Dr. Eng. Abdulsalam Alkholidi b,c, Prof. Dr. Habib Hamam d,
PhD Afrim Alimeti e
a Software Engineering Department, Canadian Institute of Technology, Albania
b Software Engineering Department Canadian Institute of Technology, Albania
c Electrical Engineering Department Faculty of Engineering – Sana’a University - Yemen
d Département de Génie Électrique, Faculté D'Ingénierie, Université de Moncton, Canada
e Industrial Engineering Department, Canadian Institute of Technology, Albania

Abstract
Deep Learning (DL) is a subfield of Machine Learning (ML) that deals with algorithms inspired by the
structure and function of the brain. DL uses complex algorithms and deep neural nets to train a model.
It consists of the learning of artificial neural networks that consider algorithms inspired by the human
brain by learning how to use a large amount of data. It includes machine learning, where machines can
learn by experience and get skills without human intervention. The importance of deep learning is the
ability to process a large number of characteristics allowing deep and powerful learning when dealing
with ambiguous data. This paper aims to study and analyze to be updated existing papers related to
the deep learning field and introduce our contribution. An additional aim of this review paper is to
concentrate on the self-driving cars case study and introduce the new approach with high performance.

Keywords: Neural Network, Architectures, Big Data, Machine Learning, Autonomous Driving

1. Introduction The limitations of deep learning are data,

We start this study by mentioning an Artificial
Neural Network (ANN) is a part of computer
architecture or system that is designed to
emulate the way information is analyzed and
interpreted by the human brain. It is the basis of
artificial intelligence (AI) and solves problems
that are hard or impossible to be done by human
or statistical standards. The main remarkable
difference between deep learning and classical
machine learning is its execution with a large
size of data. When data is few, deep learning
algorithms do not proceed well. This is due to deep
learning algorithms demanding a large quantity
of data to recognize them. We can introduce the
most important examples or applications of deep
learning as follows: Machine translation, virtual
assistants, visual recognition, self-driving cars
and drones, robotics, facial recognition, medicine
and pharmaceuticals, customer service, fraud
detection, news aggregation, digital marketing,
natural language processing, colorizing videos and
images, military, and health care. The evolutionary
history of DL started several years ago.
computational power which has of cores as
compared to CPUs, and training times. Artificial
Intelligence means enabling the machine to think
while ML has the statistical tool that explores and
analyzes the data and can be supervised by the
past labeled data and considered as a subset of AI,
unsupervised clustering, and reinforcement semi
supervising. Machine learning was developed
from object recognition in essence. It assumes
that smart machines should be able to learn and
adjust to their climate through experience [1-
3]. Deep learning is a subset of ML and creates
multi neural networks architecture and has
various techniques as Artificial Neural Network,
Convolutional Neural Network (CNN), and
Recurrent Neural Network (RNN). However, Data
Science (DS) technique applies all previous ones
and uses some mathematical tools like statistics,
probability, linear algebra, and differential
calculus. An artificial neural network consists of
several interconnected, functional elements, or
neurons that perform and process the information
by using parallel information-processors, to solve
and classify problems by regression method. The
idea is to split the feed in data into discrete value
or classes that maps inputs to outputs.

16
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

DL is based on the functioning of the human brain.
Let’s understand how a Biological Neural Network
(BNT) looks like (dendrite, cell nucleus, axon, and
synapse) where Artificial Neuron contains input,
nodes, weights, and output. There are several
steps to process the perceptron learning model
are given as demonstrated in Fig. 1:
• Step 1 calculating the weighted sum of the inputs.
• Step 2 passes the calculated weighted sum as in
the input to the activation function to generate the
output [4-5].
Function, Threshold Function, ReLU Function, and
Hyperbolic Tangent Function, and the output differ
from one activation function to another. Moreover,
the activation function requires nonlinearity.
The most used activation function is the Sigmoid
Function because it exists between (0 to1). It
is used for models where we have to predict the
probability as an output. It exists between 0 and 1
as shown in Fig, 2.

Fig. 2. Activation functions [6].

There are three layers: input layer, hidden layer,

Fig. 1. The Perceptron Learning Model.
and output layer, respectively.
If we compare between traditional machine
The inputs could be pixels values of an image (x1,
learning and deep learning algorithms, the last
x2, x3,……, xn), these values can be 256 or 512
one’s performance is increasing the amount of data
pixels.
while the traditional one becomes approximately
constant when it reaches the threshold of training
• Step 3 all inputs values are multiplied by the
data [7]. Top applications of deep learning are in
weight (w1,w2,w3…, wn) and are considered as
the following fields, namely: in customer support,
numeric values and could be any value.
medical care, self-driving cars (Apple, TESLA,
and NISSAN, etc), medical image processing,
In the transfer function
natural language processing, visual recognition,
- The weighted sum sigma is used as a central unit
n digital marketing, automatic machine translation
∑ = w i * xi
i=1 healthcare, fraud detection, language translations,
and pixel restoration photo descriptions,
- Then bias is added where the basis is common for
demographic and election predictions, deep
each neuron (1 basis/ neuron).
dreaming, and robot navigation. This study will
include some of these applications.
• Step 4 in the activation function:
DL is growing fast but has some limitations:
The output (step 1) of the transfer function feeds
the activation function.
• Data: where DL needs a massive volume of data
An activation function takes the “weighted sum
to train.
of input plus the bias” as the input to the function
• Computational power: training and neural
and decides whether it should be fired or not. A
network required graphical processes in units
standard integrated circuit can be seen as a digital
which have thousands of cores as computers to
network of activation functions that can be "ON"
CPUs that’s more expensive.
(1) or "OFF" (0), depending on the input. Several
• Training time: the time increasing with the
types of activation functions exist, namely: Sigmoid
17
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY
amount of data and numbers of layers in the
networks
We need deep learning to:
• Process huge amounts of data: ML algorithms
work with a huge amount of structured data but
DL algorithms can work with an enormous amount
of structured and unstructured data.
• Perform complex algorithms: ML algorithms
cannot perform complex operations. To do that
we need DL algorithms.
• Achieve the best performance with a large
amount of data: As the amount of data increases,
the performance of ML algorithms decreases.
In order to make sure that the performance of a
model is good, we need DL.
• Features extraction: ML algorithms extract
patterns based on labeled sample data, while DL
algorithms take large volumes of data as input,
analyze the input to extract features out of an
object, and identify similar objects.
Deep learning approaches are:
• Supervised learning where the input variables
introduced as X is structured to the output values
that are represented by Y using the following
function Y=f(X) [8].
• Unsupervised Learning (UL) analyzes and
clusters unlabeled data sets using machine
learning methods. These algorithms find hidden
patterns in data without the assistance of humans
(thus the term "unsupervised").
• Reinforcement learning (RL) is a branch of
machine learning that studies how intelligent
agents should operate in a given environment to
maximize the concept of cumulative reward.
• Hybrid Learning (HL) applies to systems that
allow the use of both generative (unsupervised)
and discriminatory (supervised) elements.
An artificial neural network is the functional unit
of deep learning, using artificial neural networks
which mimic the behavior of the human brain
to solve complex data-driven problems. Now,
deep learning itself is a part of machine learning
which falls under the larger umbrella of artificial
intelligence. Artificial intelligence machine
learning and deep learning are interconnected
fields where machine learning and deep learning
aid artificial intelligence by providing a set of
algorithms and neural networks to solve data-
driven problems. Deep learning uses artificial
neural networks that behave similarly to the neural
networks in the human brain. A neural network
functions when some input data is fed to it. This
data is then processed via layers of perceptron’s to
produce the desired output.
2. Literature Review
In recent times many researches have been
published toward developing deep learning
algorithms. he most reported are shown in [5,
9-20]. The IEEE transactions article developed
by Saptarshi Sengupta et al. [5] mentioned that
several problems were solved and developed by
using deep learning algorithms in the last decade -
the automated identification of data patterns; and
it can do so with a precision that far exceeds that of
human beings. Outside the world of conventional,
handcrafted computers, it has solved problems
algorithms of learning about aching of patients for
practitioners attempting to make sense of the data
flow that is now inundating our society.
In the paper developed by Katleho L Masita et
al., they discussed some of the most relevant
and recent advances and contributions made to
the study of the use of deep learning in object
detection. In addition, as seen, the results of
multiple studies indicate that the application of
deep learning in object detection greatly exceeds
traditional methods based on handcrafted
and learned characteristics [9]. Another paper
published by Aman Bhalla et al. [10] illustrated
a computer vision model that learns from video
data is proposed in this research work. It includes
image processing, image augmentation, behavioral
cloning, and neural network model convolution.
The architecture of the neural network used to
detect paths in a video segment, road linings,
obstacle positions, and behavioral cloning is used
for the model to learn in the video from human
behavior.
We summarize some researches published recently
on deep learning as demonstrated in Table I.
18
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

TABLE I. SUMMARY OF SOME RESEARCHES IN DEEP LEARNING

Involved Authors Findings & Conclusions Ref
Saptarshi Sengupta The article introduces an overview of multilayer artificial neural networks that contain [5]
et al deep learning. They also demonstrated some new automatic architecture optimization
protocols that use multi-agent approaches. In addition, authors the combined swarm
intelligence in Deep Learning approaches and how the influence of one enriches other
when applied to real-world problems
Ben Bright Benuwa This article studies and analyzes the principles regarding learning algorithms for deep [11]
et al. architectures. In addition, this study shows the prior work conducted in deep learning.
There still remains a great deal of work to be done in improving the learning process.
Xiaoxuan Liu This study explores the diagnostic accuracy of deep learning algorithms versus healthcare [12]
professionals in classifying diseases using medical imaging. This paper improved in quality
of published previously researches. 58 (71%) of the 82 studies satisfying the inclusion
criteria were newly identified in the updated search, suggesting that the past year has
seen a substantial increase in the number of studies comparing algorithm accuracy with
healthcare professionals.
Ajay Shrestha, and The study reviews some optimization methods to develop the accuracy of the training [13]
Ausif Mahmood and minimize training time. The authors search into the mathematics beyond training
algorithms used in existing deep networks. They tested some state-of-the-art ways to
overcome these challenges with different optimization algorithms.
Antonio Hernández- The main objective of this study is to distinguish the educational data mining tasks that [14]
Blanco et al. have benefited from Deep Learning of recently published research and to illustrate some
of the existing state-of-the-art and setting the future aspects of this important field of
research.
Mohamed (Behada) The main goal of the suggested structure is to enhance the accuracy and hasten recognition [15]
Jamshidi et al. and classification of the issues created by the virus by utilizing DL-based methods. The
proposed structures and platforms in this study are suitable for dealing with COVID-19
issues. Several methods have been developed, incorporating COVID-19's diagnostic
systems, such as LSTM, GAN, ELM, and RNN.
Jürgen Schmidhuber This study is reviewed deep supervised and unsupervised learning, reinforcement [16]
learning and evolutionary computation, and an indirect quest for deep and wide networks
encoding short programs. The main goal of this study is to assign credit to those who
contributed to the present state of the art.
Yann LeCun The most used form of ML, deep or not, is supervised learning. Authors want to build a [17]
et al. system that can classify images that contain: a house, a car, a person, or a pet. The first step
is to collect a large data set of related objects, each labeled with a specific category. During
training, the machine shows an image and produces an output in the form of a vector of
scores, one for each category.
Reem Ibrahim Hasan This review paper shows the recently published studies, developed over three years [18]
et al. leading up to 2020, for training, increasing, feature fusion and extraction, crop recognition
and counting, and plant disease detection. It includes how these techniques can be used to
feed deep classifiers and their effects on the accuracy of classifiers.

During the last decade, self-driving vehicle
technology has developed remarkably despite
some obstacles encountered, that will be inevitably
overcome shortly. The second part of this study
will focus on this self-driving vehicle algorithm.
This means that we will introduce the recently
published studies as related work. Then we will
introduce our contribution through the series of
simulations we released. The article published
by Sorin Grigorescu et al. has introduced an
overview of deep learning techniques using
autonomous driving. The performance survey and
computational requirements serve as a system-
level design reference for AI-based self-driving
cars [19], where authors started by introducing
self-driving AI-based architectures, convolutional
and repetitive neural networks, and a deep
reinforcement learning model. The method is
based on surveyed driving scene perception,
path planning, behavior judging, and motion
control algorithms. Researchers investigated both
standard planning pipeline and perception, where

19
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

each method is built using deep learning methods,
and End2End systems as well, which directly map
sensory information to steering commands that
connect sensory information directly to directional
commands.
In the article developed by Jelena Kocić et al. [20],
a single solution for an end-to-end autonomous
driving deep neural network is presented. The
main goal of our work was to achieve autonomous
driving using a light deep neural network suitable
for deployment on compact car platforms. There
are many end-to-end deep neural networks used
for autonomous driving, where the input to the
machine learning algorithm is camera images and
the output is steering angle prediction, but these
convolutional neural networks are significantly
more complex than the network architecture that
they proposed.
low and high thresholds, it is accepted only if it is
connected to a strong edge (the rapid changes in
brightness). The rapport between the thresholds
is 1/2 or 1/3.
• Step 4: To create a triangle toward the view of
the car, because we know that the lane lines are
toward the car. Computing the bitwise of both
images and taking the bitwise of each homologous
pixel in both arrays ultimately makes the image
only show the region of interest traced by the
polygonal containing the task.
• Step 5: To detect straight lines and mainline. It
finds the line which describes the points best.
The image presented in Fig. 3 is converted to
grayscale color and smoothed.

3. Simulations Results And Discussion Of

The Proposed Approach: Self-Driving Car

Series of simulation results are released to show

the performance of the proposed approach.
Indeed, we concentrated on the following features
namely: line lane detection, traffic signs detection,
and steering angle. In this subsection, we are going
Fig3. Grayscale image.
to introduce each feature separately:
The region of interest, which shows a triangle in
A. Lane Line Detection
front of the car as demonstrated in Fig. 4
Detecting lane lines in the road is very important
for the car to drive. Using the camera in the front of
the car can help to detect the lane line.
To identify the lines in the road, we can use edge
detection and gradient. Edge detection is about
sharp changes in intensity in adjacent pixels
(a sharp color change). Gradient measures the
change in brightness. There is a strong gradient (0
to 255 pixel) and a small gradient (255 to 0 pixel).
Five steps are required:
Fig. 4. Region of interest.
• Step 1: To convert the image to grayscale; so, in
one channel. It is processed faster than a normal
image with three channels.
• Step 2: To reduce the noise, i.e. converting the
colors to be smoothed (blurred).
• Step 3: To determine rapid changes in over image.
Derivative f(x,y) measures adjacent changes in all
directions x and y. There are high threshold and
low thresholds. If the gradient is between the

20
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

The bitwise function called compares by bytes the The Hough Space function detects the lane line
image and the triangle image and focuses only on during road all the time. For finding lane lines,
the lane lines as shown in Fig. 5. the process just needs to work with pixels as
demonstrated in Fig. 7.

Fig. 7. Detecting lane lines.

Fig. 5. Bitwise function.
B. Traffic Signs Detection
Hough space can detect the line, by representing Traffic sign detection can be achieved successfully
all the points in lines in the Hough space graph. by deep learning. Convolution neural network
One point can be represented by one line in is the best for processing data. Fig. 8 shows the
Hough space. In this graph, we can see where the distribution of the training dataset.
lines of the point are nearly each other. Those
are represented by m and b values for the line.
Therefore, a lane line can be created by using the
“(1)”:

y =mx +b (1)

To avoid the infinitive form “(1)”, we change the

formula to [21]:

p = x cosα +y sinα (2)

Figure 6 (a & b) introduces the Hough space: (a)
Line created by the point; (b) Points represented
in Hough space.
Fig. 8. Distribution of the training dataset.
Due to performance issues and in order to make
edges between pixels more visible, the depth of
the image is changed from three-dimensional to
one-dimensional (change their color to gray) for
all the images indicated in Fig. 9.

(a) (b)

Fig. 6. Hough Space: (a) Line created by the point; (b)

Points represented in Hough Space.
Fig 9. Gray image of a traffic sign

21
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY
After changing the dimension of the image, for a
clearer difference between the edges, we need
to equalize the photo as demonstrated in Fig.
10. This helps the model find the features, as the
model should focus on the edges of the image and
differences of the pixels.
Fig. 10. Equalized traffic sign image
The entire dataset is preprocessed in the same
way, before starting the training. A very important
part diversifies, is data augmentation. Data
augmentation is a widely used technique, which
helps expand and diversify your training data,
providing an added variety of important features,
that the network needs to extract. It gives variety
to the data and gives more data for the model to
work and generalize the new data that can exist.
Some of the training data consist of width shift and
height shift (zoomed and rotated). This makes the
model learn more and train in different data. We
have used Keras for the augmentation of the data.
The result is shown in Fig. 11.
Fig 11. The result of the augmentation process
For the traffic sign, it used the leNet architecture.
The input dimensions are 32 pixels width, 32
pixels height, and one depth. LeNet architecture
is a convolution neural network structure. Google
designed it. It is used in different applications and
it is very influential even from the last obtained
result. In this model, four convolution layers using
the Relu activation function, two MaxPooling
layers, and an output layer using the Softmax
activation function, as we have a multi-class
categorization. Categorical Cross-Entropy is used
as a loss function as we need to categorize multiple
classes and check for the lowest error. After the
data is processed by the model, it is classified into
one category as numerical. Each number means a
type of traffic sign. Figure 12 shows the progress
of the training process. Epochs are the iteration,
which is executed on the data. In the last epoch,
the accuracy is 0.98 and loss is 0.05 for training
data and 0.02 for validation loss, and 0.99 for
validation accuracy. Those are very good results. It
means that we have used the right model to train
the data. It is difficult to find the right number of
nodes and hidden layers. The result shows, that
it is the best. We have tried a different number of
layers until we got the best one.
Fig. 12. Training process. Screenshot by author.
(a) (b)
Fig. 13. Plots: (a) Loss plot; (b) Accuracy plot.
Figure 13 shows two plots to present the results.
We created those two plots to see how the model
has worked to the final epochs. It shows if the
model is overfed or underfed. As the line loss and
validation loss are not too far from each other in
the last epoch (iteration), it means that the model
is good. Loss and validation loss are reduced along
the epochs and accuracy and validation accuracy
are raised, it means that the model is learning the
features well, as, in the end, this is what I need that
the model learns the features of the image and
22
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

not memorize them. Gradient descent works on

reducing the training error and regularization aim
to reduce the generalization error.

C. Steering Angle Detection

For finding a steering angle, deep learning is the
best. The model works with the data and leans the
pattern from them. Steering Angle Detection is an
important part of the self-driving car. It shows the
car how to drive on the road. It is used a Udacity
simulator. As the car has three cameras in the front
(left, center, right), which capture images in every
single step. Figure 14 shows an image taken from
the application.
(a) (b)
Fig. 17. Splitting dataset: (a) Training dataset; (b)
Validation dataset.
To produce a variety of data and make the model
focus on the pattern and not on memorizing the
data. Data augmentation helps a generalization of
the model. For example, an image can be flipped as
shown in Fig. (18 b).

Fig. 14. Udacity.

Fig. 18. Augmentation process: (a) The original image; (b)

The flipped image.

Afterward, the image should be preprocessed, its

Fig. 15. Distribution of training dataset:
No balanced dataset.
brightness should be increased. Also, it should
be smoother, with less noise, and resized to
focus on the most important features for better
performance, see Fig. (19 b).

Fig. 16. Distribution of training dataset: Balanced dataset

This dataset Fig. 15 is not balanced, so the

dataset, in this case, should be balanced firstly as
demonstrated in Fig. 16 and some of the data will
(a) (b)
be removed.
Fig. 19. Preprocessed process:
The dataset should be divided into training dataset (a) Original image; (b) Preprocessed image
and validation set, where 20% is for validation
dataset as presented in Figs. 17.
23
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY

The formula for calculating the mean square error

is [24]:

(3)

Where variable N is several data points, the first y

is the actual value and the second y is the estimated
value.

Fig. 20. NVidia architecture.

The model shown in Fig. 20 contains five

convolution layers, flatter to change the
dimensionality to one for the three fully connected
layers, and in the end is one output layer. As in
this situation, we should output the predicted Fig. 22. History of processing the data:
steering angle, which is between -1 to 1, we cannot Model processing the data.
use categorical in this case, but we can use Mean
Square Error (MSE). MSE corresponds to how far
the actual value is from the estimated value [22].
As we have large data and we need to learn more
features from images, NVidia is the best model
and a powerful neural network to be used. The
NVIDIA DRIVE PX2 driverless car platform can
perform 30 trillion deep learning operations per
second and can achieve Level4 autopilot. NVidia
is proven effective for behavioral cloning and it is
implemented in real-life cars [23]. Mean Square Fig. 23. History of processing the data: The result of the model.
Error validates how far the predicted value is from
the predicted values. By checking the distance, it The screenshot shown in Fig. 22 shows that the
can help the model to know how large the error model is working well and the loss is reducing
is and it shows the model that it needs more to along with the validation loss. The plot shows that
learn because it is making wrong predictions as the loss has been reducing all the time in each
introduced in Fig. 21. epoch and validation loss has had an increase in
epoch 3, because the model has had an error on
not predicting well the inputs, therefore the model
learns from this error and updates its parameter.
In the last epoch loss and validation, loss is a small
number, which means that the model has learned
a lot and it has had a good result on predicting. The
loss and validation loss are not too far away from
each other, so the generalization error is low as
Fig. 21. Mean Square Error. shown in Fig. 23.

24
 A REVIEW OF DEEP LEARNING FOR SELF-DRIVING CARS: CASE STUDY
Fig. 24. Result of self-driving car. Screenshot by author.
The screenshot demonstrated in Fig. 24 shows a
part of the self-driving car during the simulator.
4. Conclusion
This study showed the features of deep learning.
It helps in solving different problems that an
autonomous machine needs. This approach showed
how self-driving car has evolved in different fields.
The Main companies that used this technique are
in the race, which one will be the first to have a
self-driving car in the market. We think it will take
some more time for perfecting the self-driving
car but I think it will be the best invention of the
future. All the vehicles have cameras in their cars,
which makes creating the dataset easier. Different
self-driving test cars are around the world but
they have done some accidents. If all the vehicles
would be autonomous, from our perspective
and from the presented studies it will be a good
solution. That would make the cars communicate
with each other and make the driving easier and
safer. A self-driving car is a future and it should
be implemented, as there are many human errors
that have caused so many tragic accidents. Deep
learning is so near to implementing the level 5
autopilot. Maybe in the future, the best approach
would be combining supervised learning and
unsupervised deep learning together. Therefore,
after the generated model of supervised learning
predicts the image, the supervised model comes
into play and checks how well the prediction is
done and if the car is going in the right direction.
Proposed future work is implementing supervised
and unsupervised working together and finding
if this would work better and trying this model in
real life and finding a better technology for sensors
as well.
REFERENCES
[1] W. T. Freeman, E. C. Pasztor, and O. T. Carmichael,
“Learning low level vision,” International Journal
of Computer Vision, vol. 40, no. 1, pp. 25–47, Oct.
2000.
[2] R. Collobert and J. Weston, “A unified
architecture for natural language processing:
Deep neural networks with multitask learning,” in
Proc. of the International Conference on Machine
Learning, New York, NY, USA, July 2008, pp. 160–
167.
[3] C. M. Bishop, Pattern recognition and machine
learning, Springer, 2006.
[4] Rafael C. Gonzalez and Richard E. Woods,
Digital image processing, page 884, third edition,
Pearson Prentice Hall, 2018. https://www.
codecool.ir/extra/2020816204611411Digital.
Image.Processing.4th.Edition.www.EBooksWorld.
ir.pdf
[5] Saptarshi Sengupta et al., A Review of Deep
Learning with Special Emphasis on Architectures,
Applications and Recent Trends. IEEE
TRANSACTIONS ON XXX, VOL. XX, NO. YY, MARCH
2019.
[6]https://himanshuxd.medium.com/activation-
functions-sigmoid-relu-leaky-relu-and-
softmax-basics-for-neural-networks-and-deep-
8d9c70eed91e
[7] Amitha Mathew, P.Amudha, and S.Sivakumari],
“Deep Learning Techniques: An Overview”, In book:
Advanced Machine Learning Technologies and
Applications, DOI: 10.1007/978-981-15-3383-
9_54, January 2021. (https://www.researchgate.
net/publication/341652370_Deep_Learning_
Techniques_An_Overview#fullTextFileContent).
[8] Amitha Mathew, P.Amudha, and S.Sivakumari],
“Deep Learning Techniques: An Overview”, In book:
Advanced Machine Learning Technologies and
Applications, DOI: 10.1007/978-981-15-3383-
9_54, January 2021. (https://www.researchgate.
net/publication/341652370_Deep_Learning_
Techniques_An_Overview#fullTextFileContent.
25